光伏发电系统发电能力预测研究-电气工程专业论文.docxVIP

摘要 摘 要 I I 摘 要 太阳能以其清洁、无污染、可再生等特点越来越受到关注，光伏发电已成为当 今世界可再生能源领域的研究热点。然而，光伏功率具有不确定性和间歇性等特点， 大规模光伏并网运行会增加电网调度的难度，影响电力系统的安全、稳定及经济运 行。精确预测光伏功率是有效减缓大规模光伏并网对电网不利影响的前提，对电网 调度计划、常规能源规划和光伏发电规划等具有重要的指导意义。 本文以光伏发电功率为研究对象，通过分析光伏发电功率的影响因素，对光伏 发电系统发电能力预测问题展开研究。首先，分析了季节类型、天气类型及辐照强 度、环境温度、云量等气象因子对光伏功率的影响，确定了预测模型的输入变量， 并提出利用相似日理论确定训练样本的方法；其次，分析了传统 BP 算法的优缺点， 提出了基于动量项-陡度因子-自适应学习率的改进 BP 算法，并建立了相应的光伏功 率预测模型；然后，针对改进 BP 算法和 PSO 算法的不足，将混沌搜索和自适应变 异思想引入到粒子群算法中，以提高算法的全局收敛概率和速度，建立了基于混沌 搜索的 AMPSO-BPNN 的光伏功率预测模型，并提出利用相似日功率修正模型预测 结果的方法；最后，依托实际光伏电站和气象观测站对预测模型进行了实例验证， 并通过分析光伏出力与负荷用电间的相关性，进一步明确了光伏电站调度运行的研 究方向。 在 Microsoft Visual C++ 6.0 环境下编制了光伏发电系统功率预测软件，对比分 析了不同光伏功率预测模型的优化性能，预测结果表明所提模型及算法具有较高的 预测精度和收敛速度，且基于相似日功率的修正方法具有一定的可行性。 关 键 词 ： 光伏功率；相似日；混沌搜索；自适应变异；粒子群算法 II II Abstract Solar energy receives more and more attention because of its cleanliness, non-polluting and renewable, and photovoltaic power generation has become the hotspot in the world’s renewable energy sector. However, photovoltaic power possesses characteristics of uncertainty and intermittency, the large-scale photovoltaic grid increases the difficulty of grid scheduling, which also affects the security, stability and economic operation of power systems. Accurate prediction of photovoltaic power is premise of effectively reducing the adverse effects for power systems with large-scale photovoltaic, which also has important guiding significance on grid scheduling program, conventional energy planning, photovoltaic power generation planning and so on. In this paper, taking the photovoltaic power generation as a research object, by analyzing the impact factors of photovoltaic power, research on generating capacity prediction of the photovoltaic power is carried out. Firstly, the effects of season types, weather types and meteorological factors such as radiation intensity, ambient temperature, and cloudiness on photovoltaic power are analyzed, then the input variables of prediction model are determined, and the method that making use of simil